The main goal of this work is to demonstrate the functionality of the technique presented in
Chen, Yi-Chen, et al. "Dictionary-based face recognition from video." European conference on computer vision. Springer Berlin Heidelberg, 2012
.
This repository contains the totality of the code developed for this course, including a face extractor based on Python and OpenCV, and a MATLAB script that, in tandem with the K-SVD implementation by Ron Rubinstein, is able to successfully recognize people from clusterized sequences of video. The script contains many references to .jpg
files that constitute my dataset, which are not included in this repository (I am not at liberty to divulge them). Feel free to contact me if you need assistance in building your own dataset.
This work was developed in the context of the VVB PhD course, and constitutes one of the deliverables of the project.